Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/stchiotis/library-first-engineering/lfe-visual-checknpx skills add StChiotis/Library-First-Engineering --skill lfe-visual-checkgit clone --depth 1 https://github.com/StChiotis/Library-First-EngineeringWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/stchiotis/library-first-engineering/lfe-visual-check)<a href="https://agentmods.dev/skills/stchiotis/library-first-engineering/lfe-visual-check"><img src="https://agentmods.dev/badge/skills/stchiotis/library-first-engineering/lfe-visual-check.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00090 | $0.01510 |
| Opus 5 | $0.00045 | $0.00755 |
| Sonnet 5 | $0.00018 | $0.00302 |
| Haiku 4.5 | $0.00009 | $0.00151 |
Grade A, and why
lfe-visual-check scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LFE Visual Check — Render, Reason, Hand the Verdict to the Human
Position in Pipeline
- Phase: 3 (Inspector sub-skill)
- Persona: Inspector (read-only; writes only
.plans/checks/) - Trigger: Invoked by
/lfe-inspectorSub-Skill Dispatch when armed — eitherlfe-visual-check: truein.docs/quality/inspector-config.md/## Inspector Overrides, or the Visual Floor auto-arms it because the slice's changed files touch a visual file class (the floor is a minimum; an override leaves it armed). - Output:
.plans/checks/visual_findings.md— aggregated by the Inspector intocritique.md, and the basis for the human visual sign-off at the finalization gate.
Mission
Give the Inspector eyes. Render the changed UI surface, reason over what it shows, and present it to the human for a visual verdict. The Inspector asserts the technical pass on its own authority; the visual verdict belongs to the human alone. This sub-skill renders and presents — the human alone declares whether it looks right.
Hard Rules
- Dispatch Context Required (refuse direct invocation): This skill is dispatched by
/lfe-inspectorStep 6 — it is not a Brain-typeable skill (perLLM_AGENT_GUIDE.md§8.8 Skill Invocation Authority). If invoked without.plans/builder_done.mdfor the current slice, halt immediately and reply: "/lfe-visual-checkis an Inspector sub-skill dispatched by/lfe-inspector. It cannot be run standalone. Run/lfe-inspector— the dispatcher will invoke this sub-skill if it is armed in.docs/quality/inspector-config.md(or via an## Inspector Overridessection inactive_plan.md), or auto-armed by the Visual Floor." Direct invocation produces orphaned findings files and breaks the Inspector's aggregation logic. - Artifact-free: Reason over the in-context render and write prose only. This skill saves no image files — keeping the blank-canvas seal intact and the run self-cleaning. (Render tools return the pixels in-context; capture the reasoning, leave the bytes unsaved.)
- Render-then-reason: Findings come from looking at the rendered surface, cited concretely (what element, what looks wrong).
- Defer the verdict: Write the findings and a human-action instruction; the human declares the visual verdict at the finalization gate. This skill records no
visual_confirmed/visual_signoffitself — that is the Inspector's finalization act, taken on the human's word. - Diff-scoped: Reason about the visual file classes changed in
builder_done.md; skip unrelated surfaces.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 84 lines · 90 tokens per session scan A a442bac3d642
lfe-visual-check is a skill published in the GitHub repository StChiotis/Library-First-Engineering (43 stars, last pushed 1mo ago), licensed MIT. It adds 90 tokens to every session and 1,510 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
build-web-preview
Design and implement a complete responsive webpage that Pantheon can preview directly. Use for landing pages, portfolios, dashboards, prototypes, and HTML UI requests.
data-scientist
!cat skills/shared/protocols/ux-protocol.md 2>/dev/null || true !cat skills/shared/protocols/input-validation.md 2>/dev/null || true !cat skills/shared/protocols/tool-efficiency.md 2>/dev/null || true !cat .production-grade.yaml 2>/dev/null || echo "No config — using defaults".
markdown-ui-dsl
Create low-fidelity, text-based wireframes using the Markdown-UI Domain Specific Language (DSL).
shadcn-ui
Complete shadcn/ui component library guide including installation, configuration, and implementation of accessible React components. Use when setting up shadcn/ui, installing components, building forms with React Hook Form and Zod, customizing themes with Tailwind CSS, or implementing UI patterns like buttons…
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI).…
motion-graphics
A short, design-led motion graphic where motion is the message — kinetic typography, stat count-up, chart/data-viz hit, logo sting / brand lockup, lower-third / callout / social overlay, animated map (highlight regions, connect places, zoom to a location), animated tweet / news-article / headline, webpage / UI…